Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 300
• Descripción:
• Frecuencia: mes
• Variables: tmax, tmin, precip, longitud, latitud, altitud
• Dimensiones del mapa: 10,10
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-300.rds.xz")
summary(model)

SOM of size 10x10 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.401.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
1099  185 1019  382 1040  936  579  280   69   10 1419  995  409 1363 1283  929 
  17   18   19   20   21   22   23   24   25   26   27   28   29   30   31   32 
1069  936  454  649 1405  983 1461 1078 1068  806  759  380  322  447 1464 1379 
  33   34   35   36   37   38   39   40   41   42   43   44   45   46   47   48 
1346  750  734  312  875  511  691  698  565 1304 1763  410  745   67  635 1033 
  49   50   51   52   53   54   55   56   57   58   59   60   61   62   63   64 
1168 1082 1296 1264 1321 1203 1257  412  882 1463 1417 1516 1967 1215 1169 1304 
  65   66   67   68   69   70   71   72   73   74   75   76   77   78   79   80 
1205  990  940  660 1167  472 1564 1101 1445  945 1400  889 1171 1070 1458  191 
  81   82   83   84   85   86   87   88   89   90   91   92   93   94   95   96 
 741 1336  680  968 1336 1918  367 1855 1016  701  479  319  276  722 1077  958 
  97   98   99  100 
1655 1254 1024  499 

Comprobación de nodos vacíos:

dim_model <- 10*10;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("tmax", "tmin", "precip", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

           tmax       tmin     precip   longitud     latitud     altitud
[1,] -0.7672456 -0.8348501  0.2915467  0.4941919  0.25107496  0.38990749
[2,] -0.1462880 -0.1957130 -0.2437649 -0.4028492 -0.09864909 -0.03794298

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   altitud   latitud      tmax      tmin    precip 
0.9823016 0.9749554 0.9736865 0.9638116 0.9603890 0.9482694 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 1.00   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.00   1st Qu.:147.0   1st Qu.:  50.00   1st Qu.:  3.00  
 Median : 6.00   Median :195.0   Median :  94.00   Median : 11.00  
 Mean   : 6.48   Mean   :199.7   Mean   :  95.01   Mean   : 15.34  
 3rd Qu.: 9.00   3rd Qu.:256.0   3rd Qu.: 142.00   3rd Qu.: 22.00  
 Max.   :12.00   Max.   :403.0   Max.   : 254.00   Max.   :167.00  
     nevada           prof_nieve           longitud        latitud       
 Min.   :0.000000   Min.   :   0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.99   1st Qu.:-4.8500  
 Median :0.000000   Median :   0.0000   Median :40.96   Median :-2.4831  
 Mean   :0.000324   Mean   :   0.5021   Mean   :40.53   Mean   :-2.4032  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.14   3rd Qu.: 0.4942  
 Max.   :6.000000   Max.   :1834.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.5  
 Mean   : 415.0  
 3rd Qu.: 667.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11   Min.   :-27.00   Min.   : 66.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:126   1st Qu.: 60.00   1st Qu.: 81.0   1st Qu.:0  
 Median :10.000   Median :148   Median : 80.00   Median : 92.0   Median :0  
 Mean   : 7.336   Mean   :155   Mean   : 84.93   Mean   :101.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:176   3rd Qu.:107.00   3rd Qu.:111.8   3rd Qu.:0  
 Max.   :12.000   Max.   :350   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:41.15   1st Qu.: -8.411   1st Qu.:  27.0  
 Median :  0.0000   Median :42.44   Median : -5.472   Median :  98.0  
 Mean   :  0.4462   Mean   :41.49   Mean   : -4.768   Mean   : 178.7  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -2.039   3rd Qu.: 261.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  3.166   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.511   Mean   :217.2   Mean   :150.5   Mean   :  7.218   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:189.5   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :185.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03078   Mean   :28.37   Mean   :-16.05   Mean   : 520.2  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 3.000   1st Qu.:131.0   1st Qu.:  35.00   1st Qu.:  6.00  
 Median : 5.000   Median :168.0   Median :  70.00   Median : 15.00  
 Mean   : 6.112   Mean   :165.7   Mean   :  68.86   Mean   : 18.89  
 3rd Qu.:10.000   3rd Qu.:204.0   3rd Qu.: 103.00   3rd Qu.: 27.00  
 Max.   :12.000   Max.   :352.0   Max.   : 219.00   Max.   :167.00  
     nevada          prof_nieve           longitud        latitud       
 Min.   :0.00000   Min.   :   0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.00000   1st Qu.:   0.0000   1st Qu.:39.49   1st Qu.:-5.2892  
 Median :0.00000   Median :   0.0000   Median :41.29   Median :-2.6544  
 Mean   :0.00045   Mean   :   0.6968   Mean   :40.83   Mean   :-2.4886  
 3rd Qu.:0.00000   3rd Qu.:   0.0000   3rd Qu.:42.43   3rd Qu.: 0.5356  
 Max.   :6.00000   Max.   :1834.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  47.0  
 Median : 258.0  
 Mean   : 435.3  
 3rd Qu.: 674.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11   Min.   :-27.00   Min.   : 66.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:126   1st Qu.: 60.00   1st Qu.: 81.0   1st Qu.:0  
 Median :10.000   Median :148   Median : 80.00   Median : 92.0   Median :0  
 Mean   : 7.336   Mean   :155   Mean   : 84.93   Mean   :101.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:176   3rd Qu.:107.00   3rd Qu.:111.8   3rd Qu.:0  
 Max.   :12.000   Max.   :350   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:41.15   1st Qu.: -8.411   1st Qu.:  27.0  
 Median :  0.0000   Median :42.44   Median : -5.472   Median :  98.0  
 Mean   :  0.4462   Mean   :41.49   Mean   : -4.768   Mean   : 178.7  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -2.039   3rd Qu.: 261.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  3.166   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.511   Mean   :217.2   Mean   :150.5   Mean   :  7.218   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:189.5   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :185.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03078   Mean   :28.37   Mean   :-16.05   Mean   : 520.2  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 2.000   Min.   :187.0   Min.   : 45.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:264.0   1st Qu.:138.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 7.000   Median :286.0   Median :164.0   Median : 4.00   Median :0  
 Mean   : 7.425   Mean   :287.1   Mean   :162.3   Mean   : 6.19   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:309.0   3rd Qu.:188.0   3rd Qu.:10.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :49.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-7.8603   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.:-4.6992   1st Qu.:  43.0  
 Median : 0.00000   Median :40.38   Median :-2.3567   Median : 247.0  
 Mean   : 0.00145   Mean   :39.76   Mean   :-2.1835   Mean   : 362.9  
 3rd Qu.: 0.00000   3rd Qu.:41.52   3rd Qu.: 0.4942   3rd Qu.: 656.0  
 Max.   :35.00000   Max.   :43.36   Max.   : 4.2156   Max.   :1405.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 3.000   1st Qu.:135.0   1st Qu.:  38.00   1st Qu.: 6.00  
 Median : 5.000   Median :170.0   Median :  71.00   Median :14.00  
 Mean   : 6.092   Mean   :169.5   Mean   :  71.42   Mean   :18.18  
 3rd Qu.:10.000   3rd Qu.:205.0   3rd Qu.: 104.00   3rd Qu.:26.00  
 Max.   :12.000   Max.   :352.0   Max.   : 219.00   Max.   :88.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:39.48   1st Qu.:-5.4981  
 Median :0.000000   Median : 0.00000   Median :41.19   Median :-2.7331  
 Mean   :0.000472   Mean   : 0.06769   Mean   :40.78   Mean   :-2.5934  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.38   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 247.0  
 Mean   : 354.7  
 3rd Qu.: 628.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11   Min.   :-27.00   Min.   : 66.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:126   1st Qu.: 60.00   1st Qu.: 81.0   1st Qu.:0  
 Median :10.000   Median :148   Median : 80.00   Median : 92.0   Median :0  
 Mean   : 7.336   Mean   :155   Mean   : 84.93   Mean   :101.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:176   3rd Qu.:107.00   3rd Qu.:111.8   3rd Qu.:0  
 Max.   :12.000   Max.   :350   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:41.15   1st Qu.: -8.411   1st Qu.:  27.0  
 Median :  0.0000   Median :42.44   Median : -5.472   Median :  98.0  
 Mean   :  0.4462   Mean   :41.49   Mean   : -4.768   Mean   : 178.7  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -2.039   3rd Qu.: 261.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  3.166   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.511   Mean   :217.2   Mean   :150.5   Mean   :  7.218   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:189.5   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :185.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03078   Mean   :28.37   Mean   :-16.05   Mean   : 520.2  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 2.000   Min.   :187.0   Min.   : 45.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:264.0   1st Qu.:138.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 7.000   Median :286.0   Median :164.0   Median : 4.00   Median :0  
 Mean   : 7.425   Mean   :287.1   Mean   :162.3   Mean   : 6.19   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:309.0   3rd Qu.:188.0   3rd Qu.:10.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :49.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-7.8603   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.:-4.6992   1st Qu.:  43.0  
 Median : 0.00000   Median :40.38   Median :-2.3567   Median : 247.0  
 Mean   : 0.00145   Mean   :39.76   Mean   :-2.1835   Mean   : 362.9  
 3rd Qu.: 0.00000   3rd Qu.:41.52   3rd Qu.: 0.4942   3rd Qu.: 656.0  
 Max.   :35.00000   Max.   :43.36   Max.   : 4.2156   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -31.00   1st Qu.: 16.00  
 Median : 7.000   Median : 76.00   Median :   9.00   Median : 29.00  
 Mean   : 6.526   Mean   : 85.96   Mean   :  15.54   Mean   : 33.68  
 3rd Qu.:10.000   3rd Qu.:139.00   3rd Qu.:  63.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :167.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1055  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.77   Mean   :41.92   Mean   :-0.3115   Mean   :2111  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 3.000   1st Qu.:135.0   1st Qu.:  38.00   1st Qu.: 6.00  
 Median : 5.000   Median :170.0   Median :  71.00   Median :14.00  
 Mean   : 6.092   Mean   :169.5   Mean   :  71.42   Mean   :18.18  
 3rd Qu.:10.000   3rd Qu.:205.0   3rd Qu.: 104.00   3rd Qu.:26.00  
 Max.   :12.000   Max.   :352.0   Max.   : 219.00   Max.   :88.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:39.48   1st Qu.:-5.4981  
 Median :0.000000   Median : 0.00000   Median :41.19   Median :-2.7331  
 Mean   :0.000472   Mean   : 0.06769   Mean   :40.78   Mean   :-2.5934  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.38   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 247.0  
 Mean   : 354.7  
 3rd Qu.: 628.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11   Min.   :-27.00   Min.   : 66.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:126   1st Qu.: 60.00   1st Qu.: 81.0   1st Qu.:0  
 Median :10.000   Median :148   Median : 80.00   Median : 92.0   Median :0  
 Mean   : 7.342   Mean   :155   Mean   : 84.93   Mean   :100.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:176   3rd Qu.:107.00   3rd Qu.:111.0   3rd Qu.:0  
 Max.   :12.000   Max.   :331   Max.   :223.00   Max.   :250.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:41.15   1st Qu.: -8.411   1st Qu.:  27.0  
 Median :  0.0000   Median :42.44   Median : -5.346   Median :  98.0  
 Mean   :  0.4489   Mean   :41.50   Mean   : -4.749   Mean   : 175.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -2.039   3rd Qu.: 261.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  3.166   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip          nevada 
 Min.   : 1.00   Min.   : 37.0   Min.   :-11.0   Min.   :252.0   Min.   :0  
 1st Qu.: 2.25   1st Qu.:110.5   1st Qu.: 49.5   1st Qu.:279.2   1st Qu.:0  
 Median : 5.50   Median :127.0   Median : 78.5   Median :302.0   Median :0  
 Mean   : 6.20   Mean   :151.9   Mean   : 86.1   Mean   :309.6   Mean   :0  
 3rd Qu.:10.25   3rd Qu.:172.5   3rd Qu.:114.8   3rd Qu.:317.2   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :204.0   Max.   :422.0   Max.   :0  
   prof_nieve    longitud        latitud           altitud       
 Min.   :0    Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:0    1st Qu.:38.05   1st Qu.: -8.649   1st Qu.:  37.02  
 Median :0    Median :41.95   Median : -8.517   Median : 262.00  
 Mean   :0    Mean   :38.95   Mean   : -7.893   Mean   : 640.81  
 3rd Qu.:0    3rd Qu.:42.43   3rd Qu.: -3.781   3rd Qu.: 571.75  
 Max.   :0    Max.   :43.36   Max.   : -1.033   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:200.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 7.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.511   Mean   :217.2   Mean   :150.5   Mean   :  7.218   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:189.5   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :185.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03078   Mean   :28.37   Mean   :-16.05   Mean   : 520.2  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 2.000   Min.   :187.0   Min.   : 45.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:264.0   1st Qu.:138.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 7.000   Median :286.0   Median :164.0   Median : 4.00   Median :0  
 Mean   : 7.425   Mean   :287.1   Mean   :162.3   Mean   : 6.19   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:309.0   3rd Qu.:188.0   3rd Qu.:10.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :49.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-7.8603   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.:-4.6992   1st Qu.:  43.0  
 Median : 0.00000   Median :40.38   Median :-2.3567   Median : 247.0  
 Mean   : 0.00145   Mean   :39.76   Mean   :-2.1835   Mean   : 362.9  
 3rd Qu.: 0.00000   3rd Qu.:41.52   3rd Qu.: 0.4942   3rd Qu.: 656.0  
 Max.   :35.00000   Max.   :43.36   Max.   : 4.2156   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -31.00   1st Qu.: 16.00  
 Median : 7.000   Median : 76.00   Median :   9.00   Median : 29.00  
 Mean   : 6.526   Mean   : 85.96   Mean   :  15.54   Mean   : 33.68  
 3rd Qu.:10.000   3rd Qu.:139.00   3rd Qu.:  63.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :167.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1055  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.77   Mean   :41.92   Mean   :-0.3115   Mean   :2111  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax          tmin            precip     
 Min.   : 1.00   Min.   :  8   Min.   :-62.00   Min.   : 0.00  
 1st Qu.: 3.00   1st Qu.:152   1st Qu.: 59.00   1st Qu.: 6.00  
 Median : 5.00   Median :180   Median : 87.00   Median :16.00  
 Mean   : 6.14   Mean   :182   Mean   : 88.36   Mean   :20.45  
 3rd Qu.:10.00   3rd Qu.:214   3rd Qu.:119.00   3rd Qu.:31.00  
 Max.   :12.00   Max.   :352   Max.   :219.00   Max.   :88.00  
     nevada           prof_nieve         longitud        latitud       
 Min.   :0.000000   Min.   : 0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.0000   1st Qu.:38.37   1st Qu.:-5.6417  
 Median :0.000000   Median : 0.0000   Median :41.43   Median :-1.7869  
 Mean   :0.000308   Mean   : 0.0388   Mean   :40.72   Mean   :-2.2380  
 3rd Qu.:0.000000   3rd Qu.: 0.0000   3rd Qu.:42.85   3rd Qu.: 0.8031  
 Max.   :4.000000   Max.   :59.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  24.0  
 Median :  71.0  
 Mean   : 156.6  
 3rd Qu.: 247.0  
 Max.   :1668.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11   Min.   :-27.00   Min.   : 66.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:126   1st Qu.: 60.00   1st Qu.: 81.0   1st Qu.:0  
 Median :10.000   Median :148   Median : 80.00   Median : 92.0   Median :0  
 Mean   : 7.342   Mean   :155   Mean   : 84.93   Mean   :100.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:176   3rd Qu.:107.00   3rd Qu.:111.0   3rd Qu.:0  
 Max.   :12.000   Max.   :331   Max.   :223.00   Max.   :250.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:41.15   1st Qu.: -8.411   1st Qu.:  27.0  
 Median :  0.0000   Median :42.44   Median : -5.346   Median :  98.0  
 Mean   :  0.4489   Mean   :41.50   Mean   : -4.749   Mean   : 175.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -2.039   3rd Qu.: 261.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  3.166   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin           precip          nevada 
 Min.   : 1.00   Min.   : 37.0   Min.   :-11.0   Min.   :252.0   Min.   :0  
 1st Qu.: 2.25   1st Qu.:110.5   1st Qu.: 49.5   1st Qu.:279.2   1st Qu.:0  
 Median : 5.50   Median :127.0   Median : 78.5   Median :302.0   Median :0  
 Mean   : 6.20   Mean   :151.9   Mean   : 86.1   Mean   :309.6   Mean   :0  
 3rd Qu.:10.25   3rd Qu.:172.5   3rd Qu.:114.8   3rd Qu.:317.2   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :204.0   Max.   :422.0   Max.   :0  
   prof_nieve    longitud        latitud           altitud       
 Min.   :0    Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:0    1st Qu.:38.05   1st Qu.: -8.649   1st Qu.:  37.02  
 Median :0    Median :41.95   Median : -8.517   Median : 262.00  
 Mean   :0    Mean   :38.95   Mean   : -7.893   Mean   : 640.81  
 3rd Qu.:0    3rd Qu.:42.43   3rd Qu.: -3.781   3rd Qu.: 571.75  
 Max.   :0    Max.   :43.36   Max.   : -1.033   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt         tmax            tmin            precip           nevada 
 Min.   : 1.0   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.0   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.0   Median :129.0   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.6   Mean   :138.1   Mean   : 60.62   Mean   : 11.01   Mean   :0  
 3rd Qu.:10.0   3rd Qu.:183.0   3rd Qu.: 98.00   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.0   Max.   :253.0   Max.   :159.00   Max.   :185.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1757   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 2.000   Min.   :187.0   Min.   : 45.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:264.0   1st Qu.:138.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 7.000   Median :286.0   Median :164.0   Median : 4.00   Median :0  
 Mean   : 7.425   Mean   :287.1   Mean   :162.3   Mean   : 6.19   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:309.0   3rd Qu.:188.0   3rd Qu.:10.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :49.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-7.8603   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.:-4.6992   1st Qu.:  43.0  
 Median : 0.00000   Median :40.38   Median :-2.3567   Median : 247.0  
 Mean   : 0.00145   Mean   :39.76   Mean   :-2.1835   Mean   : 362.9  
 3rd Qu.: 0.00000   3rd Qu.:41.52   3rd Qu.: 0.4942   3rd Qu.: 656.0  
 Max.   :35.00000   Max.   :43.36   Max.   : 4.2156   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.:  11.00   1st Qu.: 6.00  
 Median : 4.000   Median :140.0   Median :  37.00   Median :12.00  
 Mean   : 5.999   Mean   :145.6   Mean   :  38.86   Mean   :13.82  
 3rd Qu.:10.000   3rd Qu.:185.0   3rd Qu.:  68.00   3rd Qu.:20.00  
 Max.   :12.000   Max.   :279.0   Max.   : 145.00   Max.   :62.00  
     nevada           prof_nieve         longitud        latitud      
 Min.   :0.000000   Min.   : 0.0000   Min.   :37.13   Min.   :-8.624  
 1st Qu.:0.000000   1st Qu.: 0.0000   1st Qu.:40.35   1st Qu.:-4.535  
 Median :0.000000   Median : 0.0000   Median :40.95   Median :-3.678  
 Mean   :0.000789   Mean   : 0.1233   Mean   :40.89   Mean   :-3.277  
 3rd Qu.:0.000000   3rd Qu.: 0.0000   3rd Qu.:41.77   3rd Qu.:-1.885  
 Max.   :6.000000   Max.   :75.0000   Max.   :43.57   Max.   : 2.482  
    altitud      
 Min.   :   4.0  
 1st Qu.: 609.0  
 Median : 704.0  
 Mean   : 735.5  
 3rd Qu.: 900.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -31.00   1st Qu.: 16.00  
 Median : 7.000   Median : 76.00   Median :   9.00   Median : 29.00  
 Mean   : 6.526   Mean   : 85.96   Mean   :  15.54   Mean   : 33.68  
 3rd Qu.:10.000   3rd Qu.:139.00   3rd Qu.:  63.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :167.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1055  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.77   Mean   :41.92   Mean   :-0.3115   Mean   :2111  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.000   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.492   Mean   :233.9   Mean   :169.3   Mean   :  6.421   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :115.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003514   Mean   :28.38   Mean   :-15.96   Mean   :131.7  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip      
 Min.   : 1.000   Min.   :  8.0   Min.   :-62.00   Min.   : 0.000  
 1st Qu.: 2.000   1st Qu.:145.0   1st Qu.: 44.00   1st Qu.: 3.000  
 Median : 4.000   Median :171.0   Median : 70.00   Median : 8.000  
 Mean   : 5.689   Mean   :171.7   Mean   : 71.31   Mean   : 9.466  
 3rd Qu.:11.000   3rd Qu.:200.0   3rd Qu.: 98.00   3rd Qu.:14.000  
 Max.   :12.000   Max.   :300.0   Max.   :174.00   Max.   :44.000  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :36.83   Min.   :-5.8728  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:39.48   1st Qu.: 0.3264  
 Median :0.000000   Median : 0.00000   Median :41.15   Median : 0.6350  
 Mean   :0.000755   Mean   : 0.04247   Mean   :40.45   Mean   : 0.8055  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.: 1.9756  
 Max.   :4.000000   Max.   :59.00000   Max.   :43.56   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 25.0  
 Median : 71.0  
 Mean   :144.4  
 3rd Qu.:196.0  
 Max.   :916.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11   Min.   :-27.00   Min.   : 66.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:126   1st Qu.: 60.00   1st Qu.: 81.0   1st Qu.:0  
 Median :10.000   Median :148   Median : 80.00   Median : 92.0   Median :0  
 Mean   : 7.342   Mean   :155   Mean   : 84.93   Mean   :100.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:176   3rd Qu.:107.00   3rd Qu.:111.0   3rd Qu.:0  
 Max.   :12.000   Max.   :331   Max.   :223.00   Max.   :250.0   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:41.15   1st Qu.: -8.411   1st Qu.:  27.0  
 Median :  0.0000   Median :42.44   Median : -5.346   Median :  98.0  
 Mean   :  0.4489   Mean   :41.50   Mean   : -4.749   Mean   : 175.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -2.039   3rd Qu.: 261.0  
 Max.   :607.0000   Max.   :43.57   Max.   :  3.166   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 42.0   Min.   :-44.00   Min.   :15.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:143.0   1st Qu.: 61.00   1st Qu.:33.00   1st Qu.:0  
 Median : 7.000   Median :184.0   Median : 92.00   Median :43.00   Median :0  
 Mean   : 7.003   Mean   :182.6   Mean   : 94.35   Mean   :44.34   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:221.0   3rd Qu.:130.00   3rd Qu.:54.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :219.00   Max.   :88.00   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :37.18   Min.   :-8.649   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:41.48   1st Qu.:-3.799   1st Qu.:  44.0  
 Median : 0.00000   Median :42.26   Median :-1.229   Median : 176.0  
 Mean   : 0.04258   Mean   :42.17   Mean   :-1.232   Mean   : 296.8  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.: 1.827   3rd Qu.: 445.0  
 Max.   :35.00000   Max.   :43.57   Max.   : 4.216   Max.   :1668.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip         nevada 
 Min.   : 1.000   Min.   : 82.0   Min.   :-17.0   Min.   : 0.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:162.0   1st Qu.: 77.0   1st Qu.: 8.0   1st Qu.:0  
 Median : 5.000   Median :189.0   Median :102.0   Median :17.0   Median :0  
 Mean   : 6.173   Mean   :192.4   Mean   :102.9   Mean   :19.8   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:221.0   3rd Qu.:129.0   3rd Qu.:29.0   3rd Qu.:0  
 Max.   :12.000   Max.   :340.0   Max.   :213.0   Max.   :68.0   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-8.649   Min.   :  1.00  
 1st Qu.: 0.00000   1st Qu.:36.85   1st Qu.:-6.949   1st Qu.: 22.00  
 Median : 0.00000   Median :42.33   Median :-5.879   Median : 58.00  
 Mean   : 0.03311   Mean   :40.26   Mean   :-5.882   Mean   : 98.91  
 3rd Qu.: 0.00000   3rd Qu.:43.36   3rd Qu.:-4.846   3rd Qu.:127.00  
 Max.   :36.00000   Max.   :43.57   Max.   :-1.008   Max.   :582.00  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip          nevada 
 Min.   : 1.00   Min.   : 37.0   Min.   :-11.0   Min.   :252.0   Min.   :0  
 1st Qu.: 2.25   1st Qu.:110.5   1st Qu.: 49.5   1st Qu.:279.2   1st Qu.:0  
 Median : 5.50   Median :127.0   Median : 78.5   Median :302.0   Median :0  
 Mean   : 6.20   Mean   :151.9   Mean   : 86.1   Mean   :309.6   Mean   :0  
 3rd Qu.:10.25   3rd Qu.:172.5   3rd Qu.:114.8   3rd Qu.:317.2   3rd Qu.:0  
 Max.   :12.00   Max.   :350.0   Max.   :204.0   Max.   :422.0   Max.   :0  
   prof_nieve    longitud        latitud           altitud       
 Min.   :0    Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:0    1st Qu.:38.05   1st Qu.: -8.649   1st Qu.:  37.02  
 Median :0    Median :41.95   Median : -8.517   Median : 262.00  
 Mean   :0    Mean   :38.95   Mean   : -7.893   Mean   : 640.81  
 3rd Qu.:0    3rd Qu.:42.43   3rd Qu.: -3.781   3rd Qu.: 571.75  
 Max.   :0    Max.   :43.36   Max.   : -1.033   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt         tmax            tmin            precip           nevada 
 Min.   : 1.0   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.0   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.0   Median :129.0   Median : 50.00   Median :  3.00   Median :0  
 Mean   : 6.6   Mean   :138.1   Mean   : 60.62   Mean   : 11.01   Mean   :0  
 3rd Qu.:10.0   3rd Qu.:183.0   3rd Qu.: 98.00   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.0   Max.   :253.0   Max.   :159.00   Max.   :185.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1757   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 2.000   Min.   :187.0   Min.   : 45.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:264.0   1st Qu.:138.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 7.000   Median :286.0   Median :164.0   Median : 4.00   Median :0  
 Mean   : 7.425   Mean   :287.1   Mean   :162.3   Mean   : 6.19   Mean   :0  
 3rd Qu.: 8.000   3rd Qu.:309.0   3rd Qu.:188.0   3rd Qu.:10.00   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :49.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-7.8603   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.:-4.6992   1st Qu.:  43.0  
 Median : 0.00000   Median :40.38   Median :-2.3567   Median : 247.0  
 Mean   : 0.00145   Mean   :39.76   Mean   :-2.1835   Mean   : 362.9  
 3rd Qu.: 0.00000   3rd Qu.:41.52   3rd Qu.: 0.4942   3rd Qu.: 656.0  
 Max.   :35.00000   Max.   :43.36   Max.   : 4.2156   Max.   :1405.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.:  11.00   1st Qu.: 6.00  
 Median : 4.000   Median :140.0   Median :  37.00   Median :12.00  
 Mean   : 5.999   Mean   :145.6   Mean   :  38.86   Mean   :13.82  
 3rd Qu.:10.000   3rd Qu.:185.0   3rd Qu.:  68.00   3rd Qu.:20.00  
 Max.   :12.000   Max.   :279.0   Max.   : 145.00   Max.   :62.00  
     nevada           prof_nieve         longitud        latitud      
 Min.   :0.000000   Min.   : 0.0000   Min.   :37.13   Min.   :-8.624  
 1st Qu.:0.000000   1st Qu.: 0.0000   1st Qu.:40.35   1st Qu.:-4.535  
 Median :0.000000   Median : 0.0000   Median :40.95   Median :-3.678  
 Mean   :0.000789   Mean   : 0.1233   Mean   :40.89   Mean   :-3.277  
 3rd Qu.:0.000000   3rd Qu.: 0.0000   3rd Qu.:41.77   3rd Qu.:-1.885  
 Max.   :6.000000   Max.   :75.0000   Max.   :43.57   Max.   : 2.482  
    altitud      
 Min.   :   4.0  
 1st Qu.: 609.0  
 Median : 704.0  
 Mean   : 735.5  
 3rd Qu.: 900.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -31.00   1st Qu.: 16.00  
 Median : 7.000   Median : 76.00   Median :   9.00   Median : 29.00  
 Mean   : 6.526   Mean   : 85.96   Mean   :  15.54   Mean   : 33.68  
 3rd Qu.:10.000   3rd Qu.:139.00   3rd Qu.:  63.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :167.00  
     nevada    prof_nieve         longitud        latitud           altitud    
 Min.   :0   Min.   :   0.00   Min.   :40.78   Min.   :-4.0103   Min.   :1055  
 1st Qu.:0   1st Qu.:   0.00   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.00   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.77   Mean   :41.92   Mean   :-0.3115   Mean   :2111  
 3rd Qu.:0   3rd Qu.:   0.00   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.00   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 64.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212.0   1st Qu.:150.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.000   Median :233.0   Median :168.0   Median :  1.000   Median :0  
 Mean   : 6.492   Mean   :233.9   Mean   :169.3   Mean   :  6.421   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.:  7.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :115.000   Max.   :0  
   prof_nieve           longitud        latitud          altitud     
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14.0  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25.0  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33.0  
 Mean   :0.0003514   Mean   :28.38   Mean   :-15.96   Mean   :131.7  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64.0  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)